Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
Fetch raw OHLCV price data using the aipa CLI. Use this skill whenever the user asks for price data, candle data, OHLCV data, historical prices, stock quotes, crypto prices, moving averages, volume data, or any raw market data without AI analysis. Also use for: top performers, worst performers, best stocks, top gainers, biggest losers, market movers, ranking tickers by price change / volume / value / MA scores / money flow (`aipa performers`); volume profile, POC, point of control, value area, support/resistance by volume, volume-by-price histogram (`aipa volume-profile`). Also use for fundamental data: company info, financial ratios, PE, PB, ROE, NPL, CAR, fundamental ranking and screening (`aipa fundamentals info/ratios/rank/screen`). Also use when the user wants to inspect what data is available, build charts, perform their own calculations, or get numbers for a spreadsheet. Even if the user doesn't mention "aipa", trigger this skill for any raw financial data, fundamental data, or market ranking request.
Multi-agent deep research for comprehensive market analysis using the aipa CLI. Use this skill when the user asks for deep research, thorough market analysis, sector-wide investigation, comprehensive stock comparison, or detailed financial report. This runs a supervisor → parallel workers → aggregator → reviewer pipeline that takes longer but produces more thorough results than a simple analyze. Trigger for requests like "research banking sector", "deep dive into real estate stocks", or "comprehensive market overview". Can also incorporate fundamental analysis (PE, ROE, NPL, CAR, financial ratios) via `aipa fundamentals` when the user asks for fundamental context alongside technical research.
Archery SQL audit platform CLI for managing SQL workflows, queries, instances, diagnostics. Use when the user asks about SQL审核, database operations, Archery platform management, or needs to submit/review/execute SQL against database instances.
Install and connect the Azure Cost Management App (by Microsoft Corporation) in Power BI Service via browser automation. Use this skill whenever the user mentions installing, deploying, connecting, or configuring the Azure Cost Management template app in Power BI, or when they want to connect Power BI to their EA (Enterprise Agreement) enrollment for cost visibility. Also triggers when the user says "connect your data" on the Cost Management App, wants to set up EA cost data in Power BI, or needs to link an enrollment number to a Power BI cost report.
Builds Getis-Ord Gi* hotspot analysis workflows in CARTO. Triggers when the user mentions hotspots, coldspots, spatial clusters, Getis-Ord, Gi*, cluster detection, concentration areas, "where do X cluster", spacetime hotspot, temporal clusters, time-varying patterns, hotspot trends, emerging hotspots, Mann-Kendall, or wants to find statistically significant spatial or spatiotemporal patterns in point or grid data.
Builds territory planning workflows in CARTO combining territory balancing and location allocation. Triggers when the user mentions territory balancing, territory planning, sales territories, service zones, workload distribution, balanced territories, location allocation, facility placement, optimal locations, maximize coverage, minimize cost, minimize travel distance, depot placement, hub placement, warehouse siting, response time optimization, demand coverage, or wants to divide an area into balanced regions or find optimal facility locations.
Builds trade area and catchment analysis workflows in CARTO. Triggers when the user mentions trade area, catchment area, isochrone, site selection, where to open, best location, billboard, OOH, audience targeting, drive time, walk time, coverage area, commercial hotspot, site scoring, location ranking, or wants to generate isochrones, score candidate locations, or identify the best sites for retail, advertising, or services.
Owns repositories, data sources and mapping for Compose and Compose Multiplatform apps: DTO to domain to UiModel boundaries, Ktor clients and bearer auth, WebSocket and SSE, Room, DataStore, Paging 3, offline-first and data-layer tests. Use when writing or reviewing a repository, data source, DTO, mapper, HttpClient, bearer token, WebSocket, SSE, Room DAO, migration, DataStore, PagingSource, RemoteMediator, offline cache or MockEngine test. Do NOT use for ViewModel or UI wiring (compose-feature), composables (compose-ui), the MVI contract or error tiers (compose-architecture), Gradle modules (compose-project), or commonMain vs platform splits (compose-platform).
Mine Gmail history into a local flat-file knowledge base (~/.cortex/). Use when asked to "run the cortex", "mine emails", "cortex run", "cortex dry run", "set up the cortex", "cortex from DATE", or "mine my inbox". Extracts contacts, clients, communications and knowledge facts into portable JSONL/JSON files. Requires gws CLI and ANTHROPIC_API_KEY.
Search and query your Knowledge Cortex (~/.cortex/). Use when asked to "cortex stats", "cortex search", "cortex client", "cortex contacts", "cortex export", "cortex prune", "search my knowledge base", or "what do I know about COMPANY". Queries portable JSONL/JSON files for contacts, clients, communications, and facts.
Infrastructure and practices for reproducible computational research. Covers environment management, data versioning, code documentation, and sharing protocols that enable others to reproduce your results. Use when ", " mentioned.
Troubleshoot Electric sync issues. Covers fast-loop detection from CDN/proxy cache key misconfiguration, stale cache diagnosis (StaleCacheError), MissingHeadersError from CORS misconfiguration, 409 shape expired handling, SSE proxy buffering (nginx proxy_buffering off, Caddy flush_interval -1), HTTP/1.1 6-connection limit in local dev (Caddy HTTP/2 proxy), WAL growth from replication slots (max_slot_wal_keep_size), Vercel CDN cache issues, and onError/backoff behavior. Load when shapes are not receiving updates, sync is slow, or errors appear in the console.
Set up a server-side proxy to forward Electric shape requests securely. Covers ELECTRIC_PROTOCOL_QUERY_PARAMS forwarding, server-side shape definition (table, where, params), content-encoding/content-length header cleanup, CORS configuration for electric-offset/electric-handle/electric-schema/electric-cursor headers, auth token injection, Bun fetch concurrency cap (BUN_CONFIG_MAX_HTTP_REQUESTS default 256), ELECTRIC_SECRET/SOURCE_SECRET server-side only, tenant isolation via WHERE positional params, onError 401 token refresh, and subset security (AND semantics). Load when creating proxy routes, adding auth, or configuring CORS for Electric.
Design Postgres schema and Electric shape definitions together for a new feature. Covers single-table shape constraint, cross-table joins using multiple shapes, WHERE clause design for tenant isolation, column selection for bandwidth optimization, replica mode choice (default vs full for old_value), enum casting in WHERE clauses, and txid handshake setup with pg_current_xact_id() for optimistic writes. Load when designing database tables for use with Electric shapes.
Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent, discovery rate against the advertised catalog, description fit, tool overlaps). Use when the user asks "what are agents trying to do with the MCP?", "group the intents", "which goals fail most?", "what does each cluster route to?", "when agents have this intent do they find my tool?", "which tools get mixed up?", wants to recompute the clustering, or pastes an MCP analytics intent-clustering URL.
Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions had errors?", "who is connecting to my MCP?", or pastes an MCP analytics sessions URL.
Build a starting-point taxonomy for an MCP tool — what users were trying to accomplish before they reached the tool — and publish it as a PostHog notebook. Reconstructs each session's goal from its opening tool calls, then clusters those goals into named categories with size, share, and facet mix. Use when the user asks "why do people use this tool?", "what are users actually trying to do?", "what problem brings people here?", "where do these sessions start?", "segment usage of <tool> by goal", or wants a Clio-style taxonomy of MCP usage. Complements exploring-mcp-intent-clusters, which groups what agents did per call rather than why the session began. The agent running this skill writes the goal labels itself, reading the corpus query output session by session — the bundled scripts cover the mechanical facets but measurably lose the goal's altitude, so do not delegate that field to them.
Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool has the highest error rate?", "what's the slowest tool?", "which tools fail most often?", "how reliable is tool X?", wants a tool-quality matrix, or pastes an MCP analytics tool-quality / dashboard URL and asks what it shows.
Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling into individual recordings, and turning real, corroborated issues into PostHog tasks, insights, or an investigating-replay hand-off.\nTRIGGER when: user wants to pull/read/triage Replay Vision observations, asks \"what has my scanner found\", wants to act on or summarize scanner findings, turn observations into tasks/work, or points at a /replay-vision/<scanner-id> URL.\nDO NOT TRIGGER when: creating or sizing a scanner (use creating-replay-vision-scanners), running a one-off scan you don't then analyse, or authoring a signals scout.
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid + MatchIt + WeightIt + cobalt + ebal + grf + DoubleML + mediation + marginaleffects + modelsummary + kableExtra + gt + ggplot2 + ggpubr + cowplot + binsreg. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step R pipeline an applied economist runs on every paper — (1) data import & cleaning (read_dta/read_csv, naniar, janitor, validate-merges), (2) variable construction (mutate/across/winsorize/group_by + lag/lead with dplyr), (3) descriptive statistics & Table 1 (gtsummary, modelsummary::datasummary, tableone), (4) classical diagnostic tests (shapiro/jarque.bera.test/bptest/dwtest/bgtest/vif/adf.test/kpss.test/Hausman), (5) baseline modeling (fixest::feols, ivreg, did::att_gt, eventstudyr, sun_ab, did_imputation, synthdid, rdrobust, MatchIt, WeightIt, grf::causal_forest, DoubleML, mediation), (6) robustness battery (modelsummary stack, clubSandwich CRSE, fwildclusterboot, ri2, robomit Oster, bacondecomp, HonestDiD), (7) further analysis (interactions + marginaleffects, mediation::mediate, gsem via lavaan, dose-response splines, grf CATE), (8) publication-ready tables & figures (modelsummary, kableExtra, gt, stargazer, texreg, flextable to LaTeX/Word/HTML; ggplot2 + ggpubr + cowplot + binsreg + iplot for figures). **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation, IPTW + g-formula + TMLE doubly-robust triplet via `WeightIt` / `gfoRmula` / `tmle` / `ltmle`, Mendelian randomization via `MendelianRandomization` / `TwoSampleMR` / `MRPRESSO`, KM / Cox / AFT / RMST survival via `survival` / `survminer` / `flexsurv`, E-value sensitivity via `EValue`, principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `DoubleML`, S/T/X/R/DR meta-learners via `causalweight` / `grf`, causal forest via `grf::causal_forest`, BART/BCF via `bartCause` / `bcf`, matrix completion via `MCPanel`, CATE distribution + policy tree via `policytree`, off-policy evaluation, conformal causal via `conformalInference` / `cfcausal`, fairness audit via `fairmodels`, DAG learning via `pcalg` / `bnlearn` / LLM-assisted). Use when the user asks for a complete R empirical analysis, wants a tidyverse-style reproducible R script / Quarto workflow, prefers fixest over reghdfe, needs the R counterpart to StatsPAI / 00.1 / 00.2, or names a specific R step in isolation ("feols with cluster", "MatchIt nearest neighbor", "bacondecomp in R", "gtsummary table 1", "modelsummary to Word"). Mode A triggers on "target trial emulation R", "tmle ltmle", "MendelianRandomization", "TwoSampleMR", "MRPRESSO", "survival cox AFT", "STROBE R", "EValue R", "公共健康 R", "流行病学 R". Mode B triggers on "DoubleML R", "grf causal forest", "policytree", "bartCause bcf", "conformal causal R", "fairmodels", "pcalg NOTEARS", "因果机器学习 R".
Build RAG systems, semantic search, and document clustering with Gemini embeddings API (gemini-embedding-001). Generate 768-3072 dimension embeddings for vector search, integrate with Cloudflare Vectorize, and use 8 task types (RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, SEMANTIC_SIMILARITY) for optimized retrieval. Use when: implementing vector search with Google embeddings, building retrieval-augmented generation systems, creating semantic search features, clustering documents by meaning, integrating embeddings with Cloudflare Vectorize, optimizing dimension sizes (128-3072), or troubleshooting dimension mismatch errors, incorrect task type selections, rate limit issues (100 RPM free tier), vector normalization mistakes, or text truncation errors (2,048 token limit).
Produce an implementable JAX, Flax, and Optax training recipe with explicit PRNG management, pure functions, jit/vmap/pmap usage, gradient computation, Flax state handling, checkpointing, and debugging checks. Use when implementing a model in JAX/Flax, porting from PyTorch, debugging tracing/shape/NaN issues, or designing research code that uses JAX transformations.
Searches, reads and counts application logs in Elasticsearch through Kibana with the kibana-cli command line: logs by service, level, trace id, text or field value over a time range, one whole log document, error counts per service or level, counts over time, and Kibana's data views, index fields, dashboards and saved searches. Use when the user asks about logs in Kibana or ELK, an error or exception in a service, a trace id or request id, how often something happened, or which indices and fields exist. Not for changing anything in Kibana or Elasticsearch (it only reads), not for metrics or APM dashboards, and not for log files on the local disk.
Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, read and patch its code, start and stop its sandbox, poll status, list versions, delete, and share the app with humans via its PostHog URL. Use when asked to "create a streamlit app", "deploy a data app", "ship a dashboard app", "restart/stop my app", "why is my app not running", or "give me a link to the app".
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
Generates MATLAB Object Relational Mapping (ORM) code using Database Toolbox. Use when mapping MATLAB classes to database tables, reading/writing objects with ormread/ormwrite/ormupdate, defining Mappable classes, converting classes to SQL with orm2sql, or using object-oriented database workflows.
Always invoke for spatial suitability, site selection, AHP, criteria weights, or weighted-overlay work, including audits of inconsistent pairwise judgments and requests for only a final map. Covers consistency, standardization, constraints, ranked surfaces, shortlists, and sensitivity. Route travel-time placement and location-allocation to network-accessibility-analysis.
End-to-end Metabase BI development: design, build, and manage dashboards, questions (cards), snippets, and collections — as code (a dashboard kept as YAML + SQL files with pull/diff/push), with pictures and PDFs of charts and dashboards so you can check what you built, alerts and email/Slack subscriptions, change history and revert, and browser sign-in. Use this skill whenever the user mentions metabase, dashboard creation, BI dashboard, analytics dashboard, metabase question, metabase card, MBQL query, native SQL question, metabase snippet, metabase collection, visualization settings, dashboard filters, parameter mappings, dashboard screenshot/PDF, dashboard subscription, metabase alert, or wants to create/edit/manage any Metabase content. Also use when the user wants to build a reporting dashboard, KPI scorecard, or data exploration tool backed by a SQL database. Covers chart formatting, number formatting, conditional formatting, dashboard layout, and the full lifecycle: requirements → design → SQL → build → visual check → test → share. Works with multiple Metabase instances. Always use this skill for any Metabase-related task.
This skill should be used when the user asks to productionize, track, version, govern, monitor, or automate ML systems. PROACTIVELY activate for: (1) MLflow, Weights & Biases, Neptune, Comet, ClearML experiment tracking, (2) model registry, model versioning, artifact lineage, reproducibility, (3) Kubeflow, SageMaker Pipelines, Vertex AI Pipelines, Azure ML pipelines, Databricks workflows, (4) CI/CD, continuous training/evaluation, A/B tests, canary/shadow deployments, (5) drift detection, model monitoring, data validation, responsible AI governance. Provides: end-to-end MLOps architecture and operational safeguards.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.